© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1376
    Prev
    Next
    INDEX
    Explanations

    references to search functionalities and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.81
     tripod
    -0.71
     Kessler
    -0.67
     hepatitis
    -0.65
     WRITE
    -0.64
     gunmen
    -0.63
     sling
    -0.61
    peria
    -0.61
     maiden
    -0.60
     overload
    -0.59
    POSITIVE LOGITS
    terms
    0.81
    able
    0.77
    ability
    0.71
    goo
    0.71
    abe
    0.70
    soDeliveryDate
    0.70
    abil
    0.70
    Compan
    0.69
    Term
    0.68
    bot
    0.68
    Activations Density 0.058%

    No Known Activations